Deep Learning in fNIRS: A review

TL;DR

This review discusses how deep learning techniques are increasingly applied to functional Near-InfraRed Spectroscopy (fNIRS) data, improving classification accuracy and reducing preprocessing efforts in brain imaging studies.

Contribution

It provides a comprehensive overview of DL applications in fNIRS, highlighting their advantages over traditional methods and summarizing recent research findings.

Findings

Deep learning outperforms traditional machine learning in classification accuracy.

DL reduces preprocessing time and data requirements in fNIRS analysis.

Most studies report improved or comparable accuracy using DL techniques.

Abstract

Significance: Optical neuroimaging has become a well-established clinical and research tool to monitor cortical activations in the human brain. It is notable that outcomes of functional Near-InfraRed Spectroscopy (fNIRS) studies depend heavily on the data processing pipeline and classification model employed. Recently, Deep Learning (DL) methodologies have demonstrated fast and accurate performances in data processing and classification tasks across many biomedical fields. Aim: We aim to review the emerging DL applications in fNIRS studies. Approach: We first introduce some of the commonly used DL techniques. Then the review summarizes current DL work in some of the most active areas of this field, including brain-computer interface, neuro-impairment diagnosis, and neuroscience discovery. Results: Of the 63 papers considered in this review, 32 report a comparative study of deep learning techniques to traditional machine learning techniques where 26 have been shown outperforming the latter in terms of classification accuracy. Additionally, 8 studies also utilize deep learning to reduce the amount of preprocessing typically done with fNIRS data or increase the amount of data via data augmentation. Conclusions: The application of DL techniques to fNIRS studies has shown to mitigate many of the hurdles present in fNIRS studies such as lengthy data preprocessing or small sample sizes while achieving comparable or improved classification accuracy.